Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    card or identifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    -1.40
     olje
    -1.37
     Houſe
    -1.31
     Perſ
    -1.30
     magasiner
    -1.30
    ੋਂ
    -1.27
     花纹
    -1.24
    ゚
    -1.23
    suppliers
    -1.21
     cerdas
    -1.20
    POSITIVE LOGITS
     other
    1.26
    bo
    1.17
    on
    1.13
    res
    1.12
     A
    1.10
     [
    1.04
    ad
    1.03
     average
    1.02
    te
    1.00
    go
    0.99
    Act Density 0.003%

    No Known Activations